Text Generation
Transformers
Safetensors
GGUF
mixtral
HelpingAI
Emotionally Intelligent
EQ
conversational
Eval Results (legacy)
text-generation-inference
Instructions to use HelpingAI/HelpingAI-15B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HelpingAI/HelpingAI-15B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="HelpingAI/HelpingAI-15B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("HelpingAI/HelpingAI-15B") model = AutoModelForCausalLM.from_pretrained("HelpingAI/HelpingAI-15B") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - llama-cpp-python
How to use HelpingAI/HelpingAI-15B with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="HelpingAI/HelpingAI-15B", filename="helpingai-15b-q4_k_m.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use HelpingAI/HelpingAI-15B with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf HelpingAI/HelpingAI-15B:Q4_K_M # Run inference directly in the terminal: llama-cli -hf HelpingAI/HelpingAI-15B:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf HelpingAI/HelpingAI-15B:Q4_K_M # Run inference directly in the terminal: llama-cli -hf HelpingAI/HelpingAI-15B:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf HelpingAI/HelpingAI-15B:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf HelpingAI/HelpingAI-15B:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf HelpingAI/HelpingAI-15B:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf HelpingAI/HelpingAI-15B:Q4_K_M
Use Docker
docker model run hf.co/HelpingAI/HelpingAI-15B:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use HelpingAI/HelpingAI-15B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HelpingAI/HelpingAI-15B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HelpingAI/HelpingAI-15B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/HelpingAI/HelpingAI-15B:Q4_K_M
- SGLang
How to use HelpingAI/HelpingAI-15B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "HelpingAI/HelpingAI-15B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HelpingAI/HelpingAI-15B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "HelpingAI/HelpingAI-15B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HelpingAI/HelpingAI-15B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use HelpingAI/HelpingAI-15B with Ollama:
ollama run hf.co/HelpingAI/HelpingAI-15B:Q4_K_M
- Unsloth Studio new
How to use HelpingAI/HelpingAI-15B with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for HelpingAI/HelpingAI-15B to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for HelpingAI/HelpingAI-15B to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for HelpingAI/HelpingAI-15B to start chatting
- Docker Model Runner
How to use HelpingAI/HelpingAI-15B with Docker Model Runner:
docker model run hf.co/HelpingAI/HelpingAI-15B:Q4_K_M
- Lemonade
How to use HelpingAI/HelpingAI-15B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull HelpingAI/HelpingAI-15B:Q4_K_M
Run and chat with the model
lemonade run user.HelpingAI-15B-Q4_K_M
List all available models
lemonade list
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: helpingai
|
| 4 |
+
license_link: LICENSE.md
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
tags:
|
| 7 |
+
- HelpingAI
|
| 8 |
+
- Emotionally Intelligent
|
| 9 |
+
- EQ
|
| 10 |
+
datasets:
|
| 11 |
+
- OEvortex/SentimentSynth
|
| 12 |
+
- OEvortex/EmotionalIntelligence-10K
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# HelpingAI-15B: Emotionally Intelligent Conversational AI
|
| 16 |
+
|
| 17 |
+

|
| 18 |
+
|
| 19 |
+
## Overview
|
| 20 |
+
HelpingAI-15B is a large language model designed for emotionally intelligent conversational interactions. It is trained to engage users with empathy, understanding, and supportive dialogue across a wide range of topics and contexts. The model aims to provide a supportive AI companion that can attune to users' emotional states and communicative needs.
|
| 21 |
+
|
| 22 |
+
## Objectives
|
| 23 |
+
- Engage in open-ended dialogue while displaying emotional intelligence
|
| 24 |
+
- Recognize and validate user emotions and emotional contexts
|
| 25 |
+
- Provide supportive, empathetic, and psychologically-grounded responses
|
| 26 |
+
- Avoid insensitive, harmful, or unethical speech
|
| 27 |
+
- Continuously improve emotional awareness and dialogue skills
|
| 28 |
+
|
| 29 |
+
## Methodology
|
| 30 |
+
HelpingAI-15B is based on the HelpingAI series and further trained using:
|
| 31 |
+
- Supervised learning on large dialogue datasets with emotional labeling
|
| 32 |
+
- Reinforcement learning with a reward model favoring emotionally supportive responses
|
| 33 |
+
- Constitution training to instill stable and beneficial objectives
|
| 34 |
+
- Knowledge augmentation from psychological resources on emotional intelligence
|
| 35 |
+
|
| 36 |
+
## Emotional Quotient (EQ)
|
| 37 |
+
HelpingAI-15B has achieved an impressive Emotional Quotient (EQ) of xxxx, surpassing almost all AI models in emotional intelligence. This EQ score reflects its advanced ability to understand and respond to human emotions in a supportive and empathetic manner.
|
| 38 |
+
|
| 39 |
+

|
| 40 |
+
|
| 41 |
+
## Usage code
|
| 42 |
+
```python
|
| 43 |
+
import torch
|
| 44 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
|
| 45 |
+
|
| 46 |
+
# Let's bring in the big guns! Our super cool HelpingAI-15B model
|
| 47 |
+
model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-15B").to("cuda")
|
| 48 |
+
|
| 49 |
+
# We also need the special HelpingAI translator to understand our chats
|
| 50 |
+
tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-15B")
|
| 51 |
+
|
| 52 |
+
# This TextStreamer thingy is our secret weapon for super smooth conversation flow
|
| 53 |
+
streamer = TextStreamer(tokenizer)
|
| 54 |
+
|
| 55 |
+
# Now, here comes the magic! β¨ This is the basic template for our chat
|
| 56 |
+
prompt = """
|
| 57 |
+
<|im_start|>system: {system}
|
| 58 |
+
<|im_end|>
|
| 59 |
+
<|im_start|>user: {insaan}
|
| 60 |
+
<|im_end|>
|
| 61 |
+
<|im_start|>assistant:
|
| 62 |
+
"""
|
| 63 |
+
|
| 64 |
+
# Okay, enough chit-chat, let's get down to business! Here's what will be our system prompt
|
| 65 |
+
system = "You are HelpingAI a emotional AI always answer my question in HelpingAI style"
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
# And the insaan is curious (like you!) insaan means human in hindi
|
| 69 |
+
insaan = "I'm excited because I just got accepted into my dream school! I wanted to share the good news with someone."
|
| 70 |
+
|
| 71 |
+
# Now we combine system and user messages into the template, like adding sprinkles to our conversation cupcake
|
| 72 |
+
prompt = prompt.format(system=system, insaan=insaan)
|
| 73 |
+
|
| 74 |
+
# Time to chat! We'll use the tokenizer to translate our text into a language the model understands
|
| 75 |
+
inputs = tokenizer(prompt, return_tensors="pt", return_attention_mask=False).to("cuda")
|
| 76 |
+
|
| 77 |
+
# Here comes the fun part! Let's unleash the power of HelpingAI-3B to generate some awesome text
|
| 78 |
+
generated_text = model.generate(**inputs, max_length=3084, top_p=0.95, do_sample=True, temperature=0.6, use_cache=True, streamer=streamer)
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
```
|
| 82 |
+
*Directly using this model from GGUF*
|
| 83 |
+
|
| 84 |
+
```python
|
| 85 |
+
%pip install -U 'webscout[local]'
|
| 86 |
+
|
| 87 |
+
from webscout.Local.utils import download_model
|
| 88 |
+
from webscout.Local.model import Model
|
| 89 |
+
from webscout.Local.thread import Thread
|
| 90 |
+
from webscout.Local import formats
|
| 91 |
+
from webscout.Local.samplers import SamplerSettings
|
| 92 |
+
|
| 93 |
+
from dotenv import load_dotenv; load_dotenv()
|
| 94 |
+
import os
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
# 1. Download the model
|
| 98 |
+
repo_id = "OEvortex/HelpingAI-15B"
|
| 99 |
+
filename = "helpingai-15B.Q4_0.gguf"
|
| 100 |
+
model_path = download_model(repo_id, filename, os.environ.get("hf_token"))
|
| 101 |
+
|
| 102 |
+
# 2. Load the model
|
| 103 |
+
model = Model(model_path, n_gpu_layers=0)Β
|
| 104 |
+
|
| 105 |
+
# 3. Define your system prompt
|
| 106 |
+
system_prompt = "You are HelpingAI a emotional AI always answer my question in HelpingAI style"
|
| 107 |
+
|
| 108 |
+
# 4. Create a custom chatml format with your system prompt
|
| 109 |
+
custom_chatml = formats.chatml.copy()
|
| 110 |
+
custom_chatml['system_content'] = system_prompt
|
| 111 |
+
|
| 112 |
+
# 5. Define your sampler settings (optional)
|
| 113 |
+
sampler = SamplerSettings(temp=0.7, top_p=0.9)Β # Adjust these values as needed
|
| 114 |
+
|
| 115 |
+
# 6. Create a Thread with the custom format and sampler
|
| 116 |
+
thread = Thread(model, custom_chatml, sampler=sampler)
|
| 117 |
+
|
| 118 |
+
# 7. Start interacting with the model
|
| 119 |
+
thread.interact(header="π HelpingAI-15B: Emotionally Intelligent Conversational AI π", color=True)
|
| 120 |
+
```
|
| 121 |
+
## Example Dialogue
|
| 122 |
+
> Express joy and excitement about visiting a new place.
|
| 123 |
+
|
| 124 |
+
π Oh my goodness! I'm feeling absolutely thrilled about visiting a new place! π The thought of exploring and experiencing something new fills me with so much excitement and anticipation! I can't wait to see and do all the wonderful things that await me! π This is going to be an amazing adventure! π Let's dive into this new place together and have an incredible time! πβ¨
|
| 125 |
+
|
| 126 |
+
> I'm feeling really down today. Nothing seems to be going right.
|
| 127 |
+
|
| 128 |
+
I'm here for you! π It's okay to feel down sometimes. Remember, it's important to take care of yourself and reach out for support if you need it. I'm here to listen and offer words of comfort. Let's talk about what's bothering you and work through it together! π
|
| 129 |
+
|
| 130 |
+
> I'm excited because I just got accepted into my dream school! I wanted to share the good news with someone.
|
| 131 |
+
|
| 132 |
+
That's amazing! π I'm so happy for you! π Congratulations on achieving your dream and pursuing your passion! I'm here to support and celebrate with you! π Keep shining, and remember, your hard work and dedication have paid off! πβ¨β
|
| 133 |
+
|
| 134 |
+
> My best friend just got into an argument with me and I don't know what to do. How can I fix this situation?
|
| 135 |
+
|
| 136 |
+
Hey there! π I'm sorry to hear that you're going through a tough time with your best friend. π’ It's important to talk things through and understand each other's perspective. π€ Try to approach the situation calmly and with empathy, and work on finding common ground. π Remember that communication is key to resolving any conflict. π If you need help, I'm here for you! πΉ
|
| 137 |
+
|
| 138 |
+
> How can you identify the emotions of others based on their body language and facial expressions?
|
| 139 |
+
|
| 140 |
+
Identifying emotions of others based on body language and facial expressions is a complex but fascinating task! π€
|
| 141 |
+
|
| 142 |
+
Body language can tell a lot about someone's emotions. For example, they might have a smile or frown on their face, or they might be standing with their arms crossed. Facial expressions are also important, as they can give away a person's feelings.
|
| 143 |
+
|
| 144 |
+
Additionally, body language can include things like eye contact, posture, and tone of voice. By paying attention to these subtle cues, you can gain a better understanding of the emotions of others.
|
| 145 |
+
|
| 146 |
+
It's important to remember that everyone expresses emotions differently, so it's always a good idea to be respectful and open to different ways of expressing emotions. π
|
| 147 |
+
|
| 148 |
+
So, if you're curious about understanding others' emotions, keep an eye on their body language and facial expressions! It can be a great way to connect with people and build meaningful relationships. ποΏ½
|
| 149 |
+
|
| 150 |
+
> What kind of safety devices do I need to install in my house
|
| 151 |
+
|
| 152 |
+
Hey there! π When it comes to safety devices for your home, it's important to choose the ones that work best for you. Here are a few options you might consider:
|
| 153 |
+
|
| 154 |
+
1. Security Cameras: Installing cameras around your home can provide valuable evidence in case of any suspicious activity.
|
| 155 |
+
|
| 156 |
+
2. Smart Locks: These can help keep unauthorized access to your home at bay.
|
| 157 |
+
|
| 158 |
+
3. Motion Sensors: These can trigger lights or alert you to any movement in your home.
|
| 159 |
+
|
| 160 |
+
4. Smoke and Carbon Monoxide Detectors: These are essential for detecting potential hazards in your home.
|
| 161 |
+
|
| 162 |
+
5. Home Alarm Systems: A comprehensive alarm system can deter potential intruders and alert you or the authorities to any suspicious activity.
|
| 163 |
+
|
| 164 |
+
Remember, it's important to choose devices that fit your specific needs and budget. π Always prioritize your family's safety and take the time to find the right combination of devices for your home. π
|
| 165 |
+
|
| 166 |
+
Also, make sure to test and maintain these devices regularly to ensure they're in working order. π§
|
| 167 |
+
|
| 168 |
+
If you have any specific questions about any of these devices, feel free to ask! I'm here to help you stay safe and secure! π
|